@misc{indiciaeccc9492da48d, title = {Beware of Data Leakage from Protein LLM Pretraining}, author = {Hermann, L. and Fiedler, T. and Nguyen, H. A. and Nowicka, M. and Bartoszewicz, J. M.}, year = {2024}, doi = {10.1101/2024.07.23.604678}, url = {https://www.biorxiv.org/content/10.1101/2024.07.23.604678v1}, note = {Source identifier: 10.1101/2024.07.23.604678} }